Estimation of the mean time to failure relative to a class of loss functions

被引：0

作者：

Ciumara, Roxana ^{[1
]}

Beldiman, Miruna ^{[2
]}

机构：

[1] Acad Econ Studies, Dept Math, Bucharest 010572, Romania

[2] Acad Romana, Inst Math Stat & Appl Math, Bucharest 050711, Romania

来源：

BULLETIN MATHEMATIQUE DE LA SOCIETE DES SCIENCES MATHEMATIQUES DE ROUMANIE | 2007年 / 50卷 / 04期

关键词：

weighted balanced loss function; optimal estimates; Bayesian estimates; informative and non-informative priors;

D O I：

暂无

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

In this paper we consider the estimation of the mean time to failure using a weighted loss function that reflects fit and precision of estimation. The weighted loss function we propose here is an extension of weighted balanced loss function used in Rodrigues and Zellner [71 and a special case of the one used in Chung et al [1]. As in the previously mentioned article, we will prove that optimal point estimates relative to our weighted loss function are linear combination between Bayesian and non-Bayesian estimates. Examples based on non-informative and informative priors for evaluating posterior expected loss associated to alternative estimates are given. The results obtained generalize the results from Ciumara et al. [3].

引用

页码：305 / 315

页数：11